Tag Archives: AI

AI Reimbursement Is Becoming a Workflow Problem

CMS has proposed a new way to recognize and potentially pay for certain software-based clinical services (always start with the fact sheet – far more readable than the full text). This may matter in radiology, but it does not mean every AI tool will suddenly be reimbursed by Medicare.

The proposal calls these tools Software as a Medical Service. Examples include software that extracts useful information from medical images, such as heart blood-flow analysis, fracture-risk scores, or brain MRI comparisons. CMS would give some of these services their own payment category while it learns more about how they are used.

Medicare is beginning to acknowledge that some software can provide clinical information beyond a simple workflow aid, and it augments rather than replace physician work (Radiologists have been saying this for a while, and other -ologies expected to follow as product lines expand). Still, the proposal is temporary and limited. Many AI tools would not qualify for separate payment, and payment will depend on appropriate ordering, documentation, billing, and medical necessity.

Clear language matters – CMS differentiates between assistive, augmentative, and autonomous. Software that helps a radiologist work faster (assistive) is different from software that provides new, clinically useful measurements (augmentative). Both differ from a system that makes a diagnosis without a clinician (autonomous). Administrative tools such as scheduling or drafting messages can be useful, but they are not diagnostic services.

The bigger challenge is workflow. Buying or building a tool is only the beginning. All of it involve some form of cost. Hospitals must integrate it into their systems, review privacy and security, train staff, check its performance, document its use, bill correctly, manage denials, and show that it improves care. On the flip side, a billing code alone does not guarantee revenue.

For radiology leaders, the practical next step is to take inventory: Which software tools are already in use? What do they add to patient care? Are eligible services being documented and billed correctly? What do they cost, and what clinical decisions do they improve?

CMS’s proposal is a meaningful step, but not a windfall. The opportunity is to identify the software services that provide distinct value, and build reliable workflows around them.

FDA AI Guidance and the Hard Part of Transparency

The least glamorous part of AI in radiology may turn out to be the most important: telling people what changed.

That sounds simple. It is not. A diagnostic AI tool may be trained on one dataset, validated on another, deployed inside a PACS or reporting workflow, monitored after release, and then updated when the model, threshold, input, interface, or intended environment changes. Somewhere in that chain, a radiologist is expected to decide whether to trust a box, a score, a contour, a triage flag, or a sentence.

Continue reading

AI Readiness as an Educational Obligation

I wrote a guest editorial in Academic Radiology about AI readiness as a practical educational obligation, rather than an optional informatics side quest.

The piece responds to a study of medical undergraduates and radiology trainees in China, but the issue is broader: enthusiasm and exposure do not equal competence. Radiologists need enough AI literacy to recognize workflow fit, automation bias, governance gaps, and the limits of machine suggestions. Most trainees will not become model developers.

They still need to become safe, skeptical operators who can use AI with confidence and accountability in real clinical environments, worldwide, across diverse resource settings today.

When AI Saves Time but Steals Your Evening

There is a lot of AI-generated, AI-related content out there lately. This HBR article seems to stand out with interesting findings. It’s behind a paywall, but here are the takeaways.

Generative AI was supposed to buy us time. An eight-month field study inside a ~200-person U.S. tech company suggests it can do the opposite: it intensifies work.

  • First, AI lowers skill barriers, so people take on tasks they previously wouldn’t. This means designers writing code, analysts drafting research, clinicians spinning up analyses. That feels empowering, but it also creates downstream “cleanup” work for others who must review, correct, and integrate AI-assisted output.
  • Second, AI makes work frictionless enough that it seeps into the in-between moments. Lunch breaks, late evenings, the quick “one more prompt.” The result is blurrier boundaries and less real recovery.
  • Third, AI encourages parallelism: multiple drafts, multiple threads, constant checking. That boosts throughput, but it also fragments attention.

The article goes on to describe a vicious cycle in which the more your colleagues do it, the more it becomes a culture, one in which you feel compelled to keep up. Using more AI.

I’ve felt a version of this personally. A few years ago, I stopped blogging regularly to make more time for kids and life outside work. With generative AI, getting a post out is genuinely easier. It’s a idea and some prompts, edits, and reviews away. But it still has to happen sometime… which, for me, often means well into the evening, in the dark, with the quiet (adorable) snoring noises of kids nearby.

Continue reading

AI+Human Better than Human in Neurodegenerative Imaging

Recent research underscores a leap in neuroimaging accuracy for Alzheimer’s disease diagnosis, emphasizing the superior performance of AI-assisted radiologists over either AI or humans alone. This collaborative approach marries the meticulous precision of AI with the nuanced understanding of human experts, potentially setting a new standard in the detection of amyloid-related imaging abnormalities. Specifically, it demonstrated superior performance in detecting amyloid-related imaging abnormalities (ARIA), crucial for amyloid-β–directed antibody therapy. This synergy enhances diagnostic precision and underscores the potential of AI-enhanced radiological diagnostics to improve patient care significantly.

How will this synergy between AI and human intelligence redefine the future of medical diagnostics? Can this model be the blueprint for addressing other complex diseases? This breakthrough prompts us to envision a healthcare landscape where technology and human expertise converge to offer unparalleled patient care.

Detailed study can be found in JAMA Network Open.

Your Radiology AI Briefing – May 12, 2018

In this briefing:

  • Research: Machine learning algorithm predicts wait time for outpatient imaging.
  • Commercial brain imaging AI receives FDA clearance
  • Paul Chang shares insight on the future of AI
  • Dreyer and Allen publish their views on the radiology AI ecosystem
  • CB Insights publishes market research on Google’s increasing involvement in healthcare AI.

Radiology AI Briefing logo graphic

Stay up to speed in 2 minutes. Radiology AI Briefing is a semi-regular series of blog posts featuring hand-picked news stories and summaries on machine learning and data science.


Continue reading

A Simple Tool to Brainstorm AI for Your Radiology Practice

Use the AI Canvas.

Source: A Simple Tool to Start Making Decisions with the Help of AI

In a recent Harvard Business Review article, Ajay Agrawal and coauthors shared a simple tool to think about how an AI tool may be deployed.  Although the tool is no more complex than 6 boxes of free text, it does follow a number of best practices when thinking about general data and machine learning:

  1. Always define an end-goal – what’s the desired outcome?
  2. You should always make a hypothesis of what may drive this desired outcome.
  3. You should determine how to present the ML prediction in a way that drives action, not just the data itself.
  4. Your data acquisition strategy should include a feedback mechanism.

For example, this is how one might fill out the AI Canvas tool in a radiology use case:

  • Prediction: Predict whether a brian MRI for a cancer patient contains increasing or new hydrocephalus
  • Action: Label the examination as critical, and denote that AI has determined a critical finding.  For example, create an “AI-STAT” category on worklist priority.
  • Judgment: Compare the cost of interpreting this brain MRI at its usual turnaround time, versus immediately.
  • Outcome: Observe whether the action taken in response to a study labeled AI-STAT is correct.
  • Input: New MRIs of the brain MRI performed, and their prior studies.
  • Training: Historical brain MRIs
  • Feedback: Identify false positives – perhaps the prior study was from 20 years ago, or there’s been surgical resection, so that ex vacuo dilation of ventricles is not hydrocephalus.  Perhaps there has been recent surgery Identify false negatives – subtle enlargement of the temporal horns missed by AI.  Use this information to improve the AI.

How might you use this worksheet to brainstorm AI for your radiology practice?